International Journal of Internet, Broadcasting and Communication

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-Based Inverse Design for Engineering Systems: A Study on Supervised and Unsupervised Learning Models

  • Seong-Sin Kim (Assistant Professor, School of AI Convergence, Soongsil University)
  • Received : 2024.03.29
  • Accepted : 2024.04.15
  • Published : 2024.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recent studies have shown that inverse design using deep learning has the potential to rapidly generate the optimal design that satisfies the target performance without the need for iterative optimization processes. Unlike traditional methods, deep learning allows the network to rapidly generate a large number of solution candidates for the same objective after a single training, and enables the generation of diverse designs tailored to the objectives of inverse design. These inverse design techniques are expected to significantly enhance the efficiency and innovation of design processes in various fields such as aerospace, biology, medical, and engineering. We analyzes inverse design models that are mainly utilized in the nano and chemical fields, and proposes inverse design models based on supervised and unsupervised learning that can be applied to the engineering system. It is expected to present the possibility of effectively applying inverse design methodologies to the design optimization problem in the field of engineering according to each specific objective.

Keywords

References

  1. S. Molesky, Z. Lin, A. Y. Piggott, W. Jin, J. Vuckovic, and A.W. Rodriguez, "Inverse design in nanophotonics," Nature Photonics, 12(11), 659-670, 2018. DOI: https://doi.org/10.1038/s41566-018-0246-9
  2. A. Shrestha, and A. Mahmood, "Review of deep learning algorithms and architectures," IEEE Access, 7, 53040-53065, 2019. DOI: https://doi.org/10.1109/ACCESS.2019.2912200
  3. D. Liu, Y. Tan, E. Khoram, and Z. Yu, "Training deep neural networks for the inverse design of nanophotonic structures," ACS Photonics, 5(4), 1365-1369, 2018. DOI: https://doi.org/10.1021/acsphotonics.7b01377
  4. A. S. Khazaal, M. Springborg, C. Fan, K. Huwig, "Optimizing small conjugated molecules for solar-cell applications using an inverse-design method," Journal of Molecular Graphics and Modelling, 100, 107654, 2020.  DOI: https://doi.org/10.1016/j.jmgm.2020.107654
  5. T. Zhang, J. Wang, Q. Liu, J. Zhou, J. Dai, X. Han, Y. Zhou, and K. Xu, "Efficient spectrum prediction and inverse design for plasmonic waveguide systems based on artificial neural networks," Photonics Research, 7(3) 368-380, 2019. DOI: https://doi.org/10.1364/PRJ.7.000368
  6. P. E. Gill, W. Murray, and M. A. Saunders, "SNOPT: An SQP algorithm for large-scale constrained optimization," SIAM review, 47(1), 99-131, 2005. DOI: https://doi.org/10.1137/S003614450444609
  7. R. Caruana, and A. Niculescu-Mizil, "An empirical comparison of supervised learning algorithms," In Proceedings of the 23rd international conference on Machine learning, 161-168, 2006. DOI : https://doi.org/10.1145/1143844.1143865
  8. J. Peurifoy, Y. Shen, L. Jing, Y. Yang, F. Cano-Renteria, B. G. DeLacy, ... and M. Soljacic, "Nanophotonic particle simulation and inverse design using artificial neural networks," Science advances, 4(6), eaar4206, 2018. DOI: https://doi.org/10.1126/sciadv.aar4206
  9. S. Kim, M. Jwa, S. Lee, S. Park, and N. Kang, "Deep learning-based inverse design for engineering systems: multi disciplinary design optimization of automotive brakes," Structural and Multidisciplinary Optimization, 65(11), 323, 2022. DOI: https://doi.org/10.1007/s00158-022-03386-8
  10. Z. Liu, D. Zhu, S. P. Rodrigues, K. T. Lee, and W. Cai, "Generative model for the inverse design of metasurfaces," Nano letters, 18(10), 6570-6576, 2018. DOI: https://doi.org/10.1021/acs.nanolett.8b03171
  11. Y. Dan, Y. Zhao, X. Li, S. Li, M. Hu, and J. Hu, "Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials," npj Computational Materials, 6(1), 1-7, 2020. DOI: https://doi.org/10.1038/s41524-020-00352-0
  12. A. Mall, A. Patil, A. Sethi, and A. Kumar, "A cyclical deep learning based framework for simultaneous inverse and forward design of nanophotonic metasurfaces," Scientific reports, 10(1), 19427, 2020.
  13. Y. Dong, D. Li, C. Zhang, C. Wu, H. Wang, M. Xin, J. Cheng, and J. Lin, "Inverse design of two-dimensional graphene/h-BN hybrids by a regressional and conditional GAN," Carbon, 169, 9-16, 2020. DOI: https://doi.org/10.1016/j.carbon.2020.07.013
  14. W. Ma, F. Cheng, Y. Xu, Q. Wen, and Y. Liu, "Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi-Supervised Learning Strategy," Advanced Materials, 31(35), 1901111, 2019. DOI: https://doi.org/10.1002/adma.201901111
  15. Y. Zhang, and W. Ye,"Deep Learning-based inverse method for layout design," Structural and Multidisciplinary Optimization, 60, 527-536, 2019. DOI: https://doi.org/10.1007/s00158-019-02222-w
  16. C. Wang, Y. Fu, K. Deng, and C. Ji, "Functional Response Conditional Variational Auto-Encoders for Inverse Design of Metamaterials," In NeurIPS 2021 Workshop on Deep Learning and Inverse Problems, 2021.
  17. W. Jing, LI. Runze, H. E. Cheng, C. Haixin, R. Cheng, Z. Chen, and M. Zhang, "An inverse design method for supercritical airfoil based on conditional generative models," Chinese Journal of Aeronautics, 35(3), 62-74, 2022. DOI: https://doi.org/10.1016/j.cja.2021.03.006
  18. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, ... and Y. Bengio, "Generative adve rsarial nets," Advances in neural information processing systems, 27, 2014.
  19. D. P. Kingma, and M. Welling, "Auto-encoding variational bayes," arXiv preprint arXiv:1312.6114, 2013. DOI: https://doi.org/10.48550/arXiv.1312.6114
  20. M. Mirza, and S. Osindero, "Conditional generative adversarial nets," arXiv preprint arXiv:1411.1784, 2014. DOI: https://doi.org/10.48550/arXiv.1411.1784